Ana by TextQL

Converts natural language questions into SQL queries that execute against user-controlled databases without transmitting raw data to external servers. The system maintains schema awareness of connected databases and generates syntactically correct SQL for multiple database backends (PostgreSQL, MySQL, etc.), then executes queries locally and returns only aggregated results or visualizations rather than raw datasets.

Automatically discovers and maintains awareness of database schema structure (tables, columns, data types, relationships) to inform accurate natural language to SQL translation. The system introspects connected databases to build a queryable schema representation, manages schema updates, and selectively includes relevant schema context in LLM prompts to improve query generation accuracy while staying within token budgets.

Generates syntactically correct SQL queries for multiple database systems (PostgreSQL, MySQL, SQLite, etc.) by detecting target database type and applying dialect-specific syntax rules. The system translates abstract query intent into database-specific SQL, handling differences in function names, date handling, string operations, and aggregation syntax across backends.

Transforms SQL query results into visual representations (charts, graphs, tables) with configurable styling and layout options. The system analyzes result schema and data characteristics to recommend appropriate visualization types, generates visualization specifications, and renders interactive or static visualizations based on user preferences and output format requirements.

Maintains conversation context across multiple natural language queries, allowing users to refine, filter, or expand previous queries through follow-up questions. The system preserves previous query results, schema context, and user intent across conversation turns, enabling iterative data exploration without re-specifying full context for each question.

Supports running language models locally on user infrastructure rather than relying on cloud-based API calls, enabling complete data privacy by keeping both data and model inference on-premise. The system abstracts LLM provider selection, allowing users to choose between cloud APIs (OpenAI, Anthropic) and local models (Ollama, LLaMA, Mistral) with consistent query generation interfaces.

Caches previously executed query results and reuses them for identical or similar queries, reducing database load and latency for repeated analytical questions. The system detects query similarity, manages cache invalidation based on data freshness requirements, and supports incremental updates when underlying data changes, balancing performance with result accuracy.

Exports query results and visualizations in multiple formats (CSV, JSON, Parquet, etc.) for integration with external analytics, BI, and reporting tools. The system supports standard data interchange formats and may provide direct connectors to popular tools, enabling Ana to function as a query layer feeding into existing analytics pipelines.

Manages user permissions for database access, query execution, and result visibility while maintaining audit trails of analytical activities. The system enforces role-based access control (RBAC) or attribute-based access control (ABAC) to restrict which users can query which databases and tables, and logs all query execution and result access for compliance and security monitoring.

Detects invalid or problematic SQL queries before execution, provides clear error messages explaining why queries failed, and suggests corrections or alternative approaches. The system validates query syntax, checks for schema mismatches, identifies performance issues, and translates database error messages into user-friendly explanations that guide users toward correct queries.